Skip to main content

Table 3 Result of PLSR and PC-MLR models for cellulose, hemicellulose and lignin based on optimal wavelengths

From: Nondestructive and rapid determination of lignocellulose components of biofuel pellet using online hyperspectral imaging system

Indices Model type Para Calibration set Prediction set
\(R_{\text{c}}^{2}\) RMSEC (%) \(R_{\text{p}}^{2}\) RMSEP (%)
Cellulose SPA–PC-MLR 18 0.91 2.60 0.92 2.41
SPA–PLSR 11 0.90 2.77 0.91 2.52
Hemicellulose SNV–SPA–PC-MLR 10 0.81 1.63 0.84 1.48
SNV–SPA–PLSR 8 0.79 1.69 0.80 1.63
Lignose SPA–PC-MLR 16 0.76 1.71 0.71 1.89
SPA–PLSR 12 0.75 1.76 0.65 2.06
  1. aSimilar model parameters and abbreviations as in Table 2. SPA successive projections algorithm